INDEX

Explanations

mentions of the word "generic" with high activation values

oai_token-act-pair · gpt-3.5-turbo

the word "generic" and its variations in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kers

-0.88

Bre

-0.75

=-=-=-=-=-=-=-=-

-0.72

Develop

-0.71

chie

-0.70

Mass

-0.70

oir

-0.69

tein

-0.68

 Coast

-0.68

bra

-0.68

POSITIVE LOGITS

 generic

1.08

generic

0.97

isable

0.85

 Generic

0.75

ization

0.74

Generic

0.74

 interchange

0.73

 placeholder

0.73

 replacements

0.72

 identifiable

0.71

Activations Density 0.005%

mentions of the word "generic" with high activation values

the word "generic" and its variations in various contexts

No Comments

No Known Activations